Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4090 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.5106. Min Act: -0.0001

Data Index: 1624057 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.5007. Min Act: -0.0002

Data Index: 112988 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4813. Min Act: -0.0001

Data Index: 99542 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4917. Min Act: -0.0001

Data Index: 568262 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4768. Min Act: -0.0001

Data Index: 466762 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4779. Min Act: -0.0001

Data Index: 1199202 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4817. Min Act: -0.0001

Data Index: 1623054 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4661. Min Act: -0.0001

Data Index: 802799 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4617. Min Act: -0.0001

Data Index: 640282 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4640. Min Act: -0.0001

Data Index: 6942 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4635. Min Act: -0.0001

Data Index: 992142 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4548. Min Act: -0.0002

Data Index: 59696 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4486. Min Act: -0.0001

Data Index: 66701 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4554. Min Act: -0.0001

Data Index: 271256 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4548. Min Act: -0.0001

Data Index: 331987 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4513. Min Act: -0.0001

Data Index: 1027112 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1003907 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4474. Min Act: -0.0001

Data Index: 112500 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4575. Min Act: -0.0001

Data Index: 1014970 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4449. Min Act: -0.0001

Data Index: 353799 (C4 (Web Text))

Max Activating Token Index: 827